Quick/Comparisons
A entry-level Nvidia GeForce RTX 2070 SUPER graphics card with modest workstation performance (39/100), higher power consumption. Suited for casual gaming and basic graphics tasks.
| Gaming | 32 /100 |
| Workstation | 39 /100 |
| AI/ML | 33 /100 |
| Energy Efficiency | 27 |
Looking for more comparisons?
Compare GeForce RTX →| Quick Comparison Final Score | 34 /100 |
| Graphics Processor | TU104 |
| Cores | 2560 |
| TMUs / ROPs | 160 / 64 |
| Blender GPU | 2361.66 |
| Forza Horizon 5 | 77 |
| The Witcher 3 | 109 |
| Counter-Strike 2 | 150 |
| Far Cry 6 | 91 |
| Hogwarts Legacy | 61 |
| Call of Duty | 82 |
| Ghost of Tsushima | 58 |
| Cyberpunk 2077 | 71 |
| Tomb Raider | 113 |
| Average FPS | 90 |
| 1080p High | 111 |
| 1080p Ultra | 90 |
| 1440p Ultra | 66 |
| 4K Ultra | 38 |
| Margin of Error | Low |
| GB6 Compute Score | 105349 |
| Background Blur | 166.7 img/sec |
| Face Detection | 103.3 img/sec |
| Horizon Detection | 4.21 Gpixels/sec |
| Edge Detection | 5.56 Gpixels/sec |
| Gaussian Blur | 5.58 Gpixels/sec |
| Feature Matching | 1.17 Gpixels/sec |
| Stereo Matching | 489.7 Gpixels/sec |
| Particle Physics | 13242.9 FPS |
| API | OpenCL |
| G3D Mark Score | 18141 |
| G2D Mark | 878 |
| DirectX 11 | 153 FPS |
| DirectX 12 | 67 FPS |
| GPU Compute | 7473 Ops/s |
| GB6 ML Single Precision | 16276 |
| GB6 ML Half Precision | 27406 |
| GB6 ML Quantized | 10983 |
| Image Classification (SP) | 6648 |
| Image Segmentation (HP) | 16442 |
| Image Super Resolution (Q) | 15383 |
| Face Detection (HP) | 32861 |
| Pose Estimation (Q) | 66348 |
| Text Classification (SP) | 2166 |
| Machine Translation (HP) | 4239 |
| Object Detection (SP) | 8194 |
| Depth Estimation (Q) | 26192 |
| Style Transfer (SP) | 137642 |
| Framework | ONNX |
| Backend | DirectML |
| Pixel Fill Rate | 113 GPixel/s |
| Texture Fill Rate | 283 GTexel/s |
| FLOPS (FP32) | 9.1 TFLOPS |
| Memory Type | GDDR6 |
| Memory Size | 8 GB |
| Memory Clock | 1750 MHz |
| Effective Memory Speed | 14000 Mbps |
| Bus | 256-bit |
| ECC | No |
| Memory Bandwidth | 448 GB/s |
| Interface | PCIe 3.0 x16 |
| TGP | 215 W |
| Manufacturing | TSMC |
| Fabrication Process | 12 nm |
| Die Size | 545 mm² |
| Transistor Count | 13 billion |
| Transistor Density | 23.85 MTr/mm² |
| DirectX | 12 |
| Vulkan | 1.3 |
| OpenGL | 4.6 |
| OpenCL | 3 |
| CUDA | 7.5 |
| Ray Tracing | Yes |
| DLSS | DLSS 2 |
| DisplayPort | 1.4a |
| Vendor | Nvidia |
| Build | Discrete |
| Released | July 9, 2019 |
| Case | Desktop |
| Purpose | Gaming |
| Segment | Mid-range |
| Architecture | Turing |
| GPU Codename | TU104 |
| Recommended CPU | -Intel Core i7 9700Kor above |
| Steel Nomad Lite Score | 10053 |
| Time Spy | 10167 |
| Solar Bay | 45871 |
| Port Royal | 6032 |
| Fire Strike | 25675 |
| Wild Life Extreme | 20745 |
| Night Raid | 102728 |
| Base Clock | 1605 MHz |
| Boost Clock | 1770 MHz |
| Shading Units | 2560 |
| Texture Mapping Units (TMUs) | 160 |
| Render Output Units (ROPs) | 64 |
| Compute Units (Pipelines) | 40 |
| Tensor Cores | 320 |
| Ray-tracing Cores | 40 |
| L1 Cache | 64KB per cluster |
| L2 Cache | 4MB shared |
| Instructions Per Cycle | 2 IPC |
84/100